Monthly model - Regions
Tanya Rogers
1/6/2022
library(dplyr)## Warning: package 'dplyr' was built under R version 4.1.1library(lavaan)## Warning: package 'lavaan' was built under R version 4.1.1library(DiagrammeR)## Warning: package 'DiagrammeR' was built under R version 4.1.1library(ggplot2)## Warning: package 'ggplot2' was built under R version 4.1.1library(tidyr)## Warning: package 'tidyr' was built under R version 4.1.1# For saving SEM diagrams:
library(purrr)## Warning: package 'purrr' was built under R version 4.1.1library(DiagrammeRsvg)## Warning: package 'DiagrammeRsvg' was built under R version 4.1.3library(rsvg)## Warning: package 'rsvg' was built under R version 4.1.3library(png)## Warning: package 'png' was built under R version 4.1.1library(grid)
library(ggpubr)## Warning: package 'ggpubr' was built under R version 4.1.3Import data
combined=read.csv("data/monthly_averages/monthly_data_compiled_regions.csv",stringsAsFactors = F)
cnames=read.csv("analysis/column_names_region_monthly.csv", stringsAsFactors = F)
dsub=filter(combined, Year>=1995) %>% arrange(Region,Year,Month)
focaldata=dsub[,cnames$Datacolumn]
fvars=cnames$Shortname
colnames(focaldata)=fvars
regions=unique(focaldata$region)
regionorder=c("Far West","West","North","South")
focaldata=focaldata%>%
mutate(decyear=year+(month-1)/12)
focaldata = focaldata %>%
mutate(tzoop=hcope+clad+mysid+pcope+rotif_m,
tzoop_e=hcope_e+clad_e+mysid_e+pcope_e+rotif_e,
hzoop=hcope+clad+rotif_m,
hzoop_e=hcope_e+clad_e+rotif_e,
pzoop=mysid+pcope,
pzoop_e=mysid_e+pcope_e,
turbid=-secchi)
fvars=c(fvars,"tzoop","tzoop_e",
"hzoop","hzoop_e",
"pzoop","pzoop_e","turbid")
cnames=rbind(cnames,data.frame(Longname=NA,Shortname=c("tzoop","tzoop_e",
"hzoop","hzoop_e",
"pzoop","pzoop_e","turbid"),
Diagramname=c("Total Zooplankton\nBiomass",
"Total Zooplankton\nEnergy",
"Herbivorous Zooplankton\nBiomass",
"Herbivorous Zooplankton\nEnergy",
"Predatory Zooplankton\nBiomass",
"Predatory Zooplankton\nEnergy",
"Turbidity"),
Datacolumn=NA,Log=c(rep("yes",6),"no"),
Color=c("black","black","#ED7D31","#ED7D31","#7030A0",
"#7030A0","#4472C4")))
#focal variables
varnames=c("temp","flow","turbid","dophos","din","chla","hcope","clad","amphi","pcope","mysid","rotif_m","potam","corbic","sside","cent","marfish_bsmt","estfish_bsmt","tzoop","hzoop","pzoop")
#labels for lagged vars
cnameslag=cnames
cnameslag$Shortname=paste0(cnameslag$Shortname,"_1")
cnameslag$Diagramname=paste(cnameslag$Diagramname,"(t-1)")
cnameslag=rbind(cnames,cnameslag)
source("analysis/myLavaanPlot.r")
source("analysis/semDiagramFunctions.r")Data prep
Log transform, scale.
Within and across regions.
Create set with regional monthly means removed.
#log transform
logvars=fvars[cnames$Log=="yes"]
logtrans=function(x) {
x2=x[which(!is.na(x))]
if(any(x2==0)) {log(x+min(x2[which(x2>0)],na.rm=T))}
else {log(x)}
}
focaldatalog = focaldata %>%
mutate_at(logvars,logtrans)
#scale data
fdr0=focaldatalog
tvars=fvars[-(1:3)]
#scaled within regions
fdr=fdr0 %>%
group_by(region) %>%
#scale
mutate_at(tvars,scale) %>%
#lag
mutate_at(tvars,list("1"=lag,"2"=function(x) {lag(x,2)})) %>%
ungroup() %>%
as.data.frame()
#scaled within regions, remove monthly means
fdr_ds=fdr %>%
group_by(region,month) %>%
mutate_at(tvars,list("mm"=function(x) {mean(x,na.rm = T)})) %>%
mutate_at(tvars,function(x) {x-mean(x,na.rm = T)}) %>%
ungroup() %>%
#lag
group_by(region) %>%
mutate_at(tvars,scale) %>%
mutate_at(tvars,list("1"=lag,"2"=function(x) {lag(x,2)})) %>%
ungroup() %>%
as.data.frame()
#scaled across regions
# fdr1=fdr0 %>%
# #scale
# mutate_at(tvars,scale) %>%
# #lag
# group_by(region) %>%
# mutate_at(tvars,list("1"=lag,"2"=function(x) {lag(x,2)})) %>%
# ungroup() %>%
# as.data.frame()
#scaled across regions, monthly means removed
# fdr1_ds=fdr1 %>%
# group_by(region,month) %>%
# mutate_at(tvars,list("mm"=function(x) {mean(x,na.rm = T)})) %>%
# mutate_at(tvars,function(x) {x-mean(x,na.rm = T)}) %>%
# ungroup() %>%
# #lag
# group_by(region) %>%
# mutate_at(tvars,list("1"=lag,"2"=function(x) {lag(x,2)})) %>%
# ungroup() %>%
# as.data.frame()Data availability
Exclude individual zooplankton plankton groups from zooplankton model if rare (95% of values in a region are less than the across site mean, or more than 10% of values in a region are zeros).
sside and cent have no data in FW and W.
marfish and clams excluded if 95% of values in a region are less than the across site mean, though this results in marfish being excluded from W.
FW: exclude clad, mysid, corbic, sside/cent
W: exclude clad, corbic, marfish, sside/cent
N: exclude clad, potam, marfish
S: exclude mysid, potam, marfish
dataavail=focaldata %>%
gather(var, value, 4:length(fvars)) %>%
group_by(var) %>%
mutate(varmean=mean(value, na.rm=T)) %>% ungroup() %>%
group_by(region, var) %>%
summarize(
propmissing=length(which(is.na(value)))/length(value),
propzeros=length(which(value==0))/length(which(!is.na(value))),
exclude=ifelse(quantile(value,probs = 0.95, na.rm = T)<mean(varmean),T,F)) %>%
as.data.frame()## `summarise()` has grouped output by 'region'. You can override using the `.groups` argument.#these variables should not be used (too many zeros)
filter(dataavail,propzeros>0.1 | exclude) %>% filter(var %in% c("mysid","hcope","pcope","rotif_m","clad"))## region var propmissing propzeros exclude
## 1 Far West clad 0.141025641 0.95149254 TRUE
## 2 Far West mysid 0.137820513 0.21933086 TRUE
## 3 North clad 0.012820513 0.14610390 FALSE
## 4 South mysid 0.006410256 0.08709677 TRUE
## 5 West clad 0.009615385 0.26537217 FALSEfilter(dataavail,exclude) %>% filter(var %in% c("marfish_bsmt","potam","corbic"))## region var propmissing propzeros exclude
## 1 Far West corbic 0.1410256 1.0000000 TRUE
## 2 North marfish_bsmt 0.1891026 0.9762846 TRUE
## 3 North potam 0.1378205 0.1486989 TRUE
## 4 South marfish_bsmt 0.1826923 1.0000000 TRUE
## 5 South potam 0.1378205 0.9702602 TRUE
## 6 West corbic 0.1378205 0.8066914 TRUE
## 7 West marfish_bsmt 0.1666667 0.2192308 TRUETime series plots
## Note: Using an external vector in selections is ambiguous.
## i Use `all_of(varnames)` instead of `varnames` to silence this message.
## i See <https://tidyselect.r-lib.org/reference/faq-external-vector.html>.
## This message is displayed once per session.
Other useful plots
Breakdown of total zooplankton biomass.
## Warning: Removed 272 rows containing missing values (position_stack).
Correlation between biomass and energy.
for(i in 1:length(regions)) {
dtemp=filter(fdr,region==regions[i])
print(regions[i])
print(cor(dtemp$tzoop,dtemp$tzoop_e,use = "p"))
print(cor(dtemp$hzoop,dtemp$hzoop_e,use = "p"))
print(cor(dtemp$pzoop,dtemp$pzoop_e,use = "p"))
}## [1] "Far West"
## [,1]
## [1,] 0.9967037
## [,1]
## [1,] 0.9969857
## [,1]
## [1,] 0.9996106
## [1] "North"
## [,1]
## [1,] 0.9958978
## [,1]
## [1,] 0.9945197
## [,1]
## [1,] 0.999494
## [1] "South"
## [,1]
## [1,] 0.9967635
## [,1]
## [1,] 0.9965366
## [,1]
## [1,] 0.99925
## [1] "West"
## [,1]
## [1,] 0.9964103
## [,1]
## [1,] 0.994996
## [,1]
## [1,] 0.9983814Cross-correlation matrices
(only sig correlations shown… no correction for multiple comparisons)
## Warning: `expand_scale()` is deprecated; use `expansion()` instead.
## Warning: `expand_scale()` is deprecated; use `expansion()` instead.
## Warning: `expand_scale()` is deprecated; use `expansion()` instead.
## Warning: `expand_scale()` is deprecated; use `expansion()` instead.
## Warning: `expand_scale()` is deprecated; use `expansion()` instead.
## Warning: `expand_scale()` is deprecated; use `expansion()` instead.
Other notes:
Detrended fish indices are NOT correlated in S!
Nitrate and ammonia are positively correlated, max at lag 0 all regions.
Nitrate and dophos are positively correlated, max at lag 0 all regions.
Ammonia and dophos are positively correlated, lag 0 for FW and S, ammonia lags dphos by 3 months in W and N.
Chla nitrate neg correlated, lag 0.
Chla ammonia neg correlated, lag 0.
Chla dophos relationship unclear.
High flow 2-4 month prev = high chla
Hcope lags chla by 1, positive, except FW.
Clad seem to precede chla by 2, positive.
Amphi relationship unclear, prob bc not eating chla in water column.
In N and W, chla lags potam, negative. The opposite in W.
Mysid and hcope postive, lag 0.
In S and W, hcope lags pcope, negative.
Exploratory plots
Fish-centered model (upper trophic level aggregates)
modFW='hzoop~hb1*chla_1+hs1*hzoop_1+ht1*pzoop_1+ht2*potam_1+ht3*estfish_bsmt_1+ha1*flow+ha2*temp+ha3*turbid
pzoop~pb1*hzoop_1+ps1*pzoop_1+pt1*potam_1+pt2*estfish_bsmt_1+pa1*flow+pa2*temp+pa3*turbid
estfish_bsmt~fb1*hzoop_1+fb2*pzoop_1+fs1*estfish_bsmt_1+fa1*flow+fa2*temp+fa3*turbid+ft1*marfish_bsmt_1
hb:=sqrt(hb1^2)
hs:=sqrt(hs1^2)
ht:=sqrt(ht1^2+ht2^2+ht3^2)
ha:=sqrt(ha1^2+ha2^2-ha3^2)
pb:=sqrt(pb1^2)
ps:=sqrt(ps1^2)
pt:=sqrt(pt1^2+pt2^2)
pa:=sqrt(pa1^2+pa2^2+pa3^2)
fb:=sqrt(fb1^2+fb2^2)
fs:=sqrt(fs1^2)
ft:=sqrt(ft1^2)
fa:=sqrt(fa1^2+fa2^2+fa3^2)
'
modW='hzoop~hb1*chla_1+hs1*hzoop_1+ht1*pzoop_1+ht2*potam_1+ht3*estfish_bsmt_1+ha1*flow+ha2*temp+ha3*turbid
pzoop~pb1*chla_1+pb2*hzoop_1+ps1*pzoop_1+pt1*potam_1+pt2*estfish_bsmt_1+pa1*flow+pa2*temp+pa3*turbid
estfish_bsmt~fb1*hzoop_1+fb2*pzoop_1+fs1*estfish_bsmt_1+fa1*flow+fa2*temp+fa3*turbid
hb:=sqrt(hb1^2)
hs:=sqrt(hs1^2)
ht:=sqrt(ht1^2+ht2^2+ht3^2)
ha:=sqrt(ha1^2+ha2^2-ha3^2)
pb:=sqrt(pb1^2+pb2^2)
ps:=sqrt(ps1^2)
pt:=sqrt(pt1^2+pt2^2)
pa:=sqrt(pa1^2+pa2^2+pa3^2)
fb:=sqrt(fb1^2+fb2^2)
fs:=sqrt(fs1^2)
fa:=sqrt(fa1^2+fa2^2+fa3^2)
'
modN='hzoop~hb1*chla_1+hs1*hzoop_1+ht1*pzoop_1+ht2*corbic_1+ht3*estfish_bsmt_1+ha1*flow+ha2*temp+ha3*turbid
pzoop~pb1*chla_1+pb2*hzoop_1+ps1*pzoop_1+pt1*corbic_1+pt2*estfish_bsmt_1+pa1*flow+pa2*temp+pa3*turbid
estfish_bsmt~fb1*hzoop_1+fb2*pzoop_1+fs1*estfish_bsmt_1+fa1*flow+fa2*temp+fa3*turbid+ft1*sside_1+ft2*cent_1
hb:=sqrt(hb1^2)
hs:=sqrt(hs1^2)
ht:=sqrt(ht1^2+ht2^2+ht3^2)
ha:=sqrt(ha1^2+ha2^2-ha3^2)
pb:=sqrt(pb1^2+pb2^2)
ps:=sqrt(ps1^2)
pt:=sqrt(pt1^2+pt2^2)
pa:=sqrt(pa1^2+pa2^2+pa3^2)
fb:=sqrt(fb1^2+fb2^2)
fs:=sqrt(fs1^2)
ft:=sqrt(ft1^2+ft2^2)
fa:=sqrt(fa1^2+fa2^2+fa3^2)
'
modS='hzoop~hb1*chla_1+hs1*hzoop_1+ht1*pzoop_1+ht2*corbic_1+ht3*estfish_bsmt_1+ha1*flow+ha2*temp+ha3*turbid
pzoop~pb1*chla_1+pb2*hzoop_1+ps1*pzoop_1+pt1*corbic_1+pt2*estfish_bsmt_1+pa1*flow+pa2*temp+pa3*turbid
estfish_bsmt~fb1*chla_1+fb2*hzoop_1+fb3*pzoop_1+fs1*estfish_bsmt_1+fa1*flow+fa2*temp+fa3*turbid+ft1*sside_1+ft2*cent_1
hb:=sqrt(hb1^2)
hs:=sqrt(hs1^2)
ht:=sqrt(ht1^2+ht2^2+ht3^2)
ha:=sqrt(ha1^2+ha2^2-ha3^2)
pb:=sqrt(pb1^2+pb2^2)
ps:=sqrt(ps1^2)
pt:=sqrt(pt1^2+pt2^2)
pa:=sqrt(pa1^2+pa2^2+pa3^2)
fb:=sqrt(fb1^2+fb2^2+fb3^2)
fs:=sqrt(fs1^2)
ft:=sqrt(ft1^2+ft2^2)
fa:=sqrt(fa1^2+fa2^2+fa3^2)
'
modfitFW=sem(modFW, data=filter(fdr_ds,region=="Far West"))
modfitW=sem(modW, data=filter(fdr_ds,region=="West"))
modfitN=sem(modN, data=filter(fdr_ds,region=="North"))
modfitS=sem(modS, data=filter(fdr_ds,region=="South"))
summary(modfitFW, standardized=T, rsq=T)## lavaan 0.6-9 ended normally after 18 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 28
##
## Used Total
## Number of observations 191 312
##
## Model Test User Model:
##
## Test statistic 6.605
## Degrees of freedom 5
## P-value (Chi-square) 0.252
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## hzoop ~
## chla_1 (hb1) 0.030 0.076 0.392 0.695 0.030 0.025
## hzoop_1 (hs1) 0.316 0.065 4.863 0.000 0.316 0.327
## pzoop_1 (ht1) 0.054 0.062 0.871 0.384 0.054 0.057
## potam_1 (ht2) -0.187 0.058 -3.214 0.001 -0.187 -0.210
## estfs__1 (ht3) -0.173 0.069 -2.519 0.012 -0.173 -0.172
## flow (ha1) -0.018 0.077 -0.235 0.815 -0.018 -0.016
## temp (ha2) -0.090 0.072 -1.247 0.212 -0.090 -0.085
## turbid (ha3) 0.044 0.080 0.548 0.584 0.044 0.039
## pzoop ~
## hzoop_1 (pb1) 0.050 0.067 0.744 0.457 0.050 0.049
## pzoop_1 (ps1) 0.340 0.064 5.295 0.000 0.340 0.344
## potam_1 (pt1) -0.098 0.060 -1.640 0.101 -0.098 -0.105
## estfs__1 (pt2) -0.034 0.071 -0.475 0.635 -0.034 -0.032
## flow (pa1) 0.159 0.080 1.990 0.047 0.159 0.138
## temp (pa2) -0.020 0.075 -0.271 0.786 -0.020 -0.018
## turbid (pa3) 0.225 0.083 2.718 0.007 0.225 0.193
## estfish_bsmt ~
## hzoop_1 (fb1) -0.184 0.056 -3.270 0.001 -0.184 -0.198
## pzoop_1 (fb2) 0.118 0.055 2.142 0.032 0.118 0.131
## estfs__1 (fs1) 0.341 0.060 5.668 0.000 0.341 0.353
## flow (fa1) 0.096 0.069 1.395 0.163 0.096 0.091
## temp (fa2) -0.034 0.064 -0.527 0.598 -0.034 -0.033
## turbid (fa3) 0.245 0.071 3.475 0.001 0.245 0.228
## mrfsh__1 (ft1) 0.001 0.063 0.015 0.988 0.001 0.001
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .hzoop ~~
## .pzoop -0.029 0.058 -0.508 0.612 -0.029 -0.037
## .estfish_bsmt -0.048 0.050 -0.971 0.331 -0.048 -0.070
## .pzoop ~~
## .estfish_bsmt -0.093 0.052 -1.805 0.071 -0.093 -0.132
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .hzoop 0.775 0.079 9.772 0.000 0.775 0.755
## .pzoop 0.830 0.085 9.772 0.000 0.830 0.739
## .estfish_bsmt 0.603 0.062 9.772 0.000 0.603 0.639
##
## R-Square:
## Estimate
## hzoop 0.245
## pzoop 0.261
## estfish_bsmt 0.361
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## hb 0.030 0.076 0.392 0.695 0.030 0.025
## hs 0.316 0.065 4.863 0.000 0.316 0.327
## ht 0.260 0.057 4.533 0.000 0.260 0.277
## ha 0.080 0.098 0.823 0.411 0.080 0.077
## pb 0.050 0.067 0.744 0.457 0.050 0.049
## ps 0.340 0.064 5.295 0.000 0.340 0.344
## pt 0.104 0.057 1.802 0.072 0.104 0.110
## pa 0.276 0.066 4.175 0.000 0.276 0.237
## fb 0.218 0.058 3.757 0.000 0.218 0.237
## fs 0.341 0.060 5.668 0.000 0.341 0.353
## ft 0.001 0.063 0.015 0.988 0.001 0.001
## fa 0.266 0.060 4.427 0.000 0.266 0.248summary(modfitW, standardized=T, rsq=T)## lavaan 0.6-9 ended normally after 23 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 28
##
## Used Total
## Number of observations 210 312
##
## Model Test User Model:
##
## Test statistic 0.042
## Degrees of freedom 2
## P-value (Chi-square) 0.979
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## hzoop ~
## chla_1 (hb1) 0.052 0.067 0.770 0.441 0.052 0.047
## hzoop_1 (hs1) 0.430 0.069 6.227 0.000 0.430 0.413
## pzoop_1 (ht1) 0.012 0.063 0.184 0.854 0.012 0.011
## potam_1 (ht2) -0.195 0.067 -2.914 0.004 -0.195 -0.182
## estfs__1 (ht3) 0.017 0.062 0.279 0.781 0.017 0.017
## flow (ha1) 0.236 0.070 3.370 0.001 0.236 0.203
## temp (ha2) 0.009 0.061 0.142 0.887 0.009 0.009
## turbid (ha3) -0.176 0.068 -2.609 0.009 -0.176 -0.163
## pzoop ~
## chla_1 (pb1) 0.196 0.065 3.029 0.002 0.196 0.182
## hzoop_1 (pb2) 0.104 0.067 1.557 0.119 0.104 0.103
## pzoop_1 (ps1) 0.423 0.061 6.888 0.000 0.423 0.419
## potam_1 (pt1) -0.088 0.064 -1.361 0.174 -0.088 -0.084
## estfs__1 (pt2) 0.040 0.060 0.656 0.512 0.040 0.039
## flow (pa1) -0.112 0.068 -1.651 0.099 -0.112 -0.100
## temp (pa2) 0.187 0.059 3.168 0.002 0.187 0.190
## turbid (pa3) 0.027 0.065 0.411 0.681 0.027 0.026
## estfish_bsmt ~
## hzoop_1 (fb1) 0.106 0.070 1.501 0.133 0.106 0.104
## pzoop_1 (fb2) -0.073 0.069 -1.044 0.296 -0.073 -0.071
## estfs__1 (fs1) 0.278 0.068 4.089 0.000 0.278 0.270
## flow (fa1) -0.229 0.076 -2.997 0.003 -0.229 -0.202
## temp (fa2) 0.037 0.066 0.561 0.575 0.037 0.037
## turbid (fa3) 0.242 0.071 3.396 0.001 0.242 0.228
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .hzoop ~~
## .pzoop 0.181 0.049 3.692 0.000 0.181 0.263
## .estfish_bsmt -0.073 0.054 -1.354 0.176 -0.073 -0.094
## .pzoop ~~
## .estfish_bsmt 0.127 0.053 2.412 0.016 0.127 0.169
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .hzoop 0.709 0.069 10.247 0.000 0.709 0.666
## .pzoop 0.666 0.065 10.247 0.000 0.666 0.667
## .estfish_bsmt 0.854 0.083 10.247 0.000 0.854 0.835
##
## R-Square:
## Estimate
## hzoop 0.334
## pzoop 0.333
## estfish_bsmt 0.165
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## hb 0.052 0.067 0.770 0.441 0.052 0.047
## hs 0.430 0.069 6.227 0.000 0.430 0.413
## ht 0.197 0.066 2.966 0.003 0.197 0.183
## ha 0.157 0.118 1.327 0.185 0.157 0.123
## pb 0.221 0.057 3.889 0.000 0.221 0.209
## ps 0.423 0.061 6.888 0.000 0.423 0.419
## pt 0.096 0.061 1.567 0.117 0.096 0.093
## pa 0.220 0.062 3.548 0.000 0.220 0.216
## fb 0.128 0.079 1.620 0.105 0.128 0.126
## fs 0.278 0.068 4.089 0.000 0.278 0.270
## fa 0.335 0.081 4.123 0.000 0.335 0.306summary(modfitN, standardized=T, rsq=T)## lavaan 0.6-9 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 30
##
## Used Total
## Number of observations 193 312
##
## Model Test User Model:
##
## Test statistic 4.536
## Degrees of freedom 6
## P-value (Chi-square) 0.604
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## hzoop ~
## chla_1 (hb1) 0.025 0.071 0.353 0.724 0.025 0.023
## hzoop_1 (hs1) 0.200 0.069 2.899 0.004 0.200 0.195
## pzoop_1 (ht1) 0.033 0.071 0.466 0.641 0.033 0.033
## corbic_1 (ht2) 0.020 0.067 0.296 0.767 0.020 0.019
## estfs__1 (ht3) -0.054 0.067 -0.798 0.425 -0.054 -0.057
## flow (ha1) 0.330 0.077 4.275 0.000 0.330 0.309
## temp (ha2) 0.097 0.064 1.511 0.131 0.097 0.100
## turbid (ha3) 0.177 0.069 2.574 0.010 0.177 0.172
## pzoop ~
## chla_1 (pb1) 0.255 0.068 3.747 0.000 0.255 0.235
## hzoop_1 (pb2) 0.134 0.066 2.043 0.041 0.134 0.132
## pzoop_1 (ps1) 0.283 0.068 4.163 0.000 0.283 0.279
## corbic_1 (pt1) 0.009 0.064 0.138 0.890 0.009 0.009
## estfs__1 (pt2) -0.030 0.064 -0.463 0.643 -0.030 -0.032
## flow (pa1) -0.295 0.074 -4.008 0.000 -0.295 -0.278
## temp (pa2) 0.127 0.061 2.079 0.038 0.127 0.132
## turbid (pa3) -0.010 0.066 -0.147 0.883 -0.010 -0.009
## estfish_bsmt ~
## hzoop_1 (fb1) 0.148 0.073 2.025 0.043 0.148 0.135
## pzoop_1 (fb2) 0.043 0.073 0.593 0.553 0.043 0.040
## estfs__1 (fs1) 0.127 0.070 1.822 0.068 0.127 0.127
## flow (fa1) -0.518 0.080 -6.484 0.000 -0.518 -0.454
## temp (fa2) 0.030 0.066 0.455 0.649 0.030 0.029
## turbid (fa3) 0.104 0.071 1.462 0.144 0.104 0.094
## sside_1 (ft1) -0.014 0.067 -0.214 0.831 -0.014 -0.014
## cent_1 (ft2) -0.149 0.068 -2.200 0.028 -0.149 -0.141
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .hzoop ~~
## .pzoop 0.169 0.055 3.063 0.002 0.169 0.226
## .estfish_bsmt -0.030 0.058 -0.517 0.605 -0.030 -0.037
## .pzoop ~~
## .estfish_bsmt 0.050 0.055 0.900 0.368 0.050 0.065
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .hzoop 0.781 0.079 9.823 0.000 0.781 0.787
## .pzoop 0.712 0.072 9.823 0.000 0.712 0.725
## .estfish_bsmt 0.820 0.083 9.823 0.000 0.820 0.722
##
## R-Square:
## Estimate
## hzoop 0.213
## pzoop 0.275
## estfish_bsmt 0.278
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## hb 0.025 0.071 0.353 0.724 0.025 0.023
## hs 0.200 0.069 2.899 0.004 0.200 0.195
## ht 0.066 0.076 0.866 0.387 0.066 0.069
## ha 0.295 0.106 2.769 0.006 0.295 0.276
## pb 0.289 0.066 4.358 0.000 0.289 0.270
## ps 0.283 0.068 4.163 0.000 0.283 0.279
## pt 0.031 0.065 0.474 0.636 0.031 0.033
## pa 0.322 0.069 4.661 0.000 0.322 0.308
## fb 0.154 0.068 2.262 0.024 0.154 0.141
## fs 0.127 0.070 1.822 0.068 0.127 0.127
## ft 0.150 0.067 2.219 0.026 0.150 0.142
## fa 0.529 0.081 6.498 0.000 0.529 0.465summary(modfitS, standardized=T, rsq=T)## lavaan 0.6-9 ended normally after 18 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 31
##
## Used Total
## Number of observations 199 312
##
## Model Test User Model:
##
## Test statistic 5.034
## Degrees of freedom 5
## P-value (Chi-square) 0.412
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## hzoop ~
## chla_1 (hb1) 0.244 0.074 3.301 0.001 0.244 0.225
## hzoop_1 (hs1) 0.215 0.070 3.057 0.002 0.215 0.205
## pzoop_1 (ht1) -0.025 0.078 -0.322 0.748 -0.025 -0.023
## corbic_1 (ht2) 0.094 0.071 1.311 0.190 0.094 0.087
## estfs__1 (ht3) -0.012 0.070 -0.174 0.862 -0.012 -0.012
## flow (ha1) 0.140 0.076 1.834 0.067 0.140 0.122
## temp (ha2) 0.180 0.068 2.636 0.008 0.180 0.177
## turbid (ha3) -0.037 0.069 -0.540 0.589 -0.037 -0.036
## pzoop ~
## chla_1 (pb1) 0.303 0.061 4.964 0.000 0.303 0.302
## hzoop_1 (pb2) 0.135 0.058 2.320 0.020 0.135 0.139
## pzoop_1 (ps1) 0.328 0.064 5.116 0.000 0.328 0.324
## corbic_1 (pt1) -0.066 0.058 -1.134 0.257 -0.066 -0.066
## estfs__1 (pt2) 0.028 0.058 0.490 0.624 0.028 0.030
## flow (pa1) -0.102 0.063 -1.627 0.104 -0.102 -0.097
## temp (pa2) -0.042 0.057 -0.740 0.459 -0.042 -0.044
## turbid (pa3) 0.092 0.057 1.610 0.107 0.092 0.096
## estfish_bsmt ~
## chla_1 (fb1) 0.141 0.070 2.000 0.045 0.141 0.135
## hzoop_1 (fb2) 0.144 0.067 2.166 0.030 0.144 0.143
## pzoop_1 (fb3) -0.043 0.074 -0.575 0.565 -0.043 -0.041
## estfs__1 (fs1) 0.212 0.067 3.158 0.002 0.212 0.217
## flow (fa1) -0.037 0.073 -0.510 0.610 -0.037 -0.034
## temp (fa2) -0.033 0.065 -0.511 0.609 -0.033 -0.034
## turbid (fa3) 0.217 0.069 3.164 0.002 0.217 0.219
## sside_1 (ft1) 0.055 0.065 0.846 0.398 0.055 0.055
## cent_1 (ft2) -0.078 0.067 -1.166 0.244 -0.078 -0.081
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .hzoop ~~
## .pzoop 0.099 0.052 1.899 0.058 0.099 0.136
## .estfish_bsmt 0.031 0.060 0.515 0.606 0.031 0.037
## .pzoop ~~
## .estfish_bsmt 0.139 0.050 2.767 0.006 0.139 0.200
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .hzoop 0.883 0.088 9.975 0.000 0.883 0.843
## .pzoop 0.602 0.060 9.975 0.000 0.602 0.670
## .estfish_bsmt 0.797 0.080 9.975 0.000 0.797 0.824
##
## R-Square:
## Estimate
## hzoop 0.157
## pzoop 0.330
## estfish_bsmt 0.176
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## hb 0.244 0.074 3.301 0.001 0.244 0.225
## hs 0.215 0.070 3.057 0.002 0.215 0.205
## ht 0.098 0.072 1.364 0.173 0.098 0.091
## ha 0.225 0.076 2.959 0.003 0.225 0.212
## pb 0.331 0.058 5.696 0.000 0.331 0.332
## ps 0.328 0.064 5.116 0.000 0.328 0.324
## pt 0.072 0.057 1.257 0.209 0.072 0.072
## pa 0.144 0.065 2.232 0.026 0.144 0.144
## fb 0.206 0.070 2.959 0.003 0.206 0.201
## fs 0.212 0.067 3.158 0.002 0.212 0.217
## ft 0.095 0.060 1.578 0.115 0.095 0.098
## fa 0.223 0.070 3.173 0.002 0.223 0.224#modificationindices(modfitW, sort=T, maximum.number=20)
#residuals(modfitS)
labelsfarwest=createLabels(modfitFW, cnameslag)
labelswest=createLabels(modfitW, cnameslag)
labelsnorth=createLabels(modfitN, cnameslag)
labelssouth=createLabels(modfitS, cnameslag)
#FAR WEST
myLavaanPlot(model=modfitFW, labels=labelsfarwest,
node_options=list(shape="box", fontname="Helvetica"),
coefs=TRUE, stand=TRUE, covs=FALSE, sig=0.05,
width=c("regress","latent"),
color=c("regress","latent"))upper_plot_far_west <- createGraph(fit=modfitFW,
reference_df=cnameslag,
model_type="monthly_upper_trophic",
title="Far West",
manual_port_settings=TRUE)
upper_plot_far_west#WEST
myLavaanPlot(model=modfitW, labels=labelswest,
node_options=list(shape="box", fontname="Helvetica"),
coefs=TRUE, stand=TRUE, covs=FALSE, sig=0.05,
width=c("regress","latent"),
color=c("regress","latent"))upper_plot_west <- createGraph(fit=modfitW,
reference_df=cnameslag,
model_type="monthly_upper_trophic",
title="West",
manual_port_settings=TRUE)
upper_plot_west#NORTH
myLavaanPlot(model=modfitN, labels=labelsnorth,
node_options=list(shape="box", fontname="Helvetica"),
coefs=TRUE, stand=TRUE, covs=FALSE, sig=0.05,
width=c("regress","latent"),
color=c("regress","latent"))upper_plot_north <- createGraph(fit=modfitN,
reference_df=cnameslag,
model_type="monthly_upper_trophic",
title="North",
manual_port_settings=TRUE)
upper_plot_north#SOUTH
myLavaanPlot(model=modfitS, labels=labelssouth,
node_options=list(shape="box", fontname="Helvetica"),
coefs=TRUE, stand=TRUE, covs=FALSE, sig=0.05,
width=c("regress","latent"),
color=c("regress","latent"))upper_plot_south <- createGraph(fit=modfitS,
reference_df=cnameslag,
model_type="monthly_upper_trophic",
title="South",
manual_port_settings=TRUE)
upper_plot_southSave updated SEM diagrams
Total effects
ssFW=standardizedsolution(modfitFW) %>% mutate(region="Far West")
ssW=standardizedsolution(modfitW) %>% mutate(region="West")
ssN=standardizedsolution(modfitN) %>% mutate(region="North")
ssS=standardizedsolution(modfitS) %>% mutate(region="South")
ssut=rbind(ssFW,ssW,ssN,ssS) %>% filter(op==":=") %>% select(region,lhs,est.std:ci.upper) %>%
separate(lhs,c("variable","influence"), sep=1) %>%
mutate(variable=case_when(variable=="h" ~ "herbivorous\nzooplankton",
variable=="p" ~ "predatory\nzooplankton",
variable=="f" ~ "estuarine\nfishes"),
influence=case_when(influence=="b" ~ "bottom-up",
influence=="t" ~ "top-down",
influence=="s" ~ "self-regulation",
influence=="a" ~ "abiotic drivers"),
region=factor(region, levels=regionorder),
influence=factor(influence, levels=c("self-regulation","bottom-up","top-down","abiotic drivers")),
variable=factor(variable,levels=c("estuarine\nfishes","predatory\nzooplankton","herbivorous\nzooplankton")),
sig=ifelse(pvalue<0.05,"*",""))
ggplot(ssut,aes(x=influence,y=est.std)) +
facet_grid(variable~region) +
geom_errorbar(aes(ymin=ci.lower, ymax=ci.upper),width=0.5) +
geom_point() +
geom_text(aes(y=ci.upper+0.05, label=sig)) +
geom_hline(yintercept = 0) +
theme_bw() + theme(axis.text.x=element_text(angle=90, vjust=0.5, hjust=1)) +
labs(y="total effect (standardized)")
#ggsave("../uteffects.png",width = 6,height=5)Phytoplankton-centered model (lower trophic level aggregates)
modFW='din~ns1*din_1+nt1*chla+nn1*hzoop_1+nn2*pzoop_1+nn3*potam_1+na1*flow+na2*temp+na3*turbid
chla~cb1*din_1+cs1*chla_1+ct1*hzoop_1+ct2*potam_1+ca1*flow+ca2*temp+ca3*turbid
potam~lb1*chla_1+lb2*hzoop_1+lb3*pzoop_1+ls1*potam_1+la1*flow+la2*temp+la3*turbid
ns:=sqrt(ns1^2)
nt:=sqrt(nt1^2)
nn:=sqrt(nn1^2+nn2^2+nn3^2)
na:=sqrt(na1^2+na2^2+na3^2)
cb:=sqrt(cb1^2)
cs:=sqrt(cs1^2)
ct:=sqrt(ct1^2+ct2^2)
ca:=sqrt(ca1^2+ca2^2+ca3^2)
lb:=sqrt(lb1^2+lb2^2+lb3^2)
ls:=sqrt(ls1^2)
la:=sqrt(la1^2+la2^2+la3^2)
'
modW='din~ns1*din_1+nt1*chla+nn1*hzoop_1+nn2*pzoop_1+nn3*potam_1+na1*flow+na2*temp+na3*turbid
chla~cb1*din_1+cs1*chla_1+ct1*hzoop_1+ct2*potam_1+ca1*flow+ca2*temp+ca3*turbid
potam~lb1*din_1+lb2*chla_1+lb3*hzoop_1+lb4*pzoop_1+ls1*potam_1+la1*flow+la2*temp+la3*turbid
ns:=sqrt(ns1^2)
nt:=sqrt(nt1^2)
nn:=sqrt(nn1^2+nn2^2+nn3^2)
na:=sqrt(na1^2+na2^2+na3^2)
cb:=sqrt(cb1^2)
cs:=sqrt(cs1^2)
ct:=sqrt(ct1^2+ct2^2)
ca:=sqrt(ca1^2+ca2^2+ca3^2)
lb:=sqrt(lb1^2+lb2^2+lb3^2+lb4^2)
ls:=sqrt(ls1^2)
la:=sqrt(la1^2+la2^2+la3^2)
'
modN='din~ns1*din_1+nt1*chla+nn1*hzoop_1+nn2*pzoop_1+nn3*corbic_1+na1*flow+na2*temp+na3*turbid
chla~cb1*din_1+cs1*chla_1+ct1*hzoop_1+ct2*corbic_1+ct3*pzoop_1+ca1*flow+ca2*temp+ca3*turbid
corbic~lb1*chla_1+lb2*hzoop_1+lb3*pzoop_1+ls1*corbic_1+la1*flow+la2*temp+la3*turbid
ns:=sqrt(ns1^2)
nt:=sqrt(nt1^2)
nn:=sqrt(nn1^2+nn2^2+nn3^2)
na:=sqrt(na1^2+na2^2+na3^2)
cb:=sqrt(cb1^2)
cs:=sqrt(cs1^2)
ct:=sqrt(ct1^2+ct2^2+ct3^2)
ca:=sqrt(ca1^2+ca2^2+ca3^2)
lb:=sqrt(lb1^2+lb2^2+lb3^2)
ls:=sqrt(ls1^2)
la:=sqrt(la1^2+la2^2+la3^2)
'
modS='din~ns1*din_1+nt1*chla+nn1*hzoop_1+nn2*pzoop_1+nn3*corbic_1+na1*flow+na2*temp+na3*turbid
chla~cb1*din_1+cs1*chla_1+ct1*hzoop_1+ct2*corbic_1+ca1*flow+ca2*temp+ca3*turbid
corbic~lb1*chla_1+lb2*hzoop_1+lb3*pzoop_1+ls1*corbic_1+la1*flow+la2*temp+la3*turbid
ns:=sqrt(ns1^2)
nt:=sqrt(nt1^2)
nn:=sqrt(nn1^2+nn2^2+nn3^2)
na:=sqrt(na1^2+na2^2+na3^2)
cb:=sqrt(cb1^2)
cs:=sqrt(cs1^2)
ct:=sqrt(ct1^2+ct2^2)
ca:=sqrt(ca1^2+ca2^2+ca3^2)
lb:=sqrt(lb1^2+lb2^2+lb3^2)
ls:=sqrt(ls1^2)
la:=sqrt(la1^2+la2^2+la3^2)
'
modfitFW=sem(modFW, data=filter(fdr_ds,region=="Far West"))
modfitW=sem(modW, data=filter(fdr_ds,region=="West"))
modfitN=sem(modN, data=filter(fdr_ds,region=="North"))
modfitS=sem(modS, data=filter(fdr_ds,region=="South"))
summary(modfitFW, standardized=T, rsq=T)## lavaan 0.6-9 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 26
##
## Used Total
## Number of observations 234 312
##
## Model Test User Model:
##
## Test statistic 1.283
## Degrees of freedom 4
## P-value (Chi-square) 0.864
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## din ~
## din_1 (ns1) 0.425 0.057 7.426 0.000 0.425 0.425
## chla (nt1) -0.163 0.071 -2.280 0.023 -0.163 -0.130
## hzoop_1 (nn1) 0.033 0.059 0.550 0.582 0.033 0.033
## pzoop_1 (nn2) -0.020 0.058 -0.343 0.731 -0.020 -0.020
## potam_1 (nn3) -0.006 0.057 -0.101 0.919 -0.006 -0.006
## flow (na1) -0.038 0.072 -0.522 0.602 -0.038 -0.032
## temp (na2) -0.156 0.064 -2.449 0.014 -0.156 -0.150
## turbid (na3) -0.131 0.068 -1.915 0.056 -0.131 -0.123
## chla ~
## din_1 (cb1) 0.011 0.051 0.219 0.827 0.011 0.014
## chla_1 (cs1) 0.258 0.063 4.091 0.000 0.258 0.262
## hzoop_1 (ct1) -0.013 0.053 -0.241 0.809 -0.013 -0.016
## potam_1 (ct2) -0.016 0.050 -0.320 0.749 -0.016 -0.021
## flow (ca1) 0.006 0.063 0.103 0.918 0.006 0.007
## temp (ca2) 0.122 0.056 2.182 0.029 0.122 0.146
## turbid (ca3) -0.027 0.060 -0.453 0.651 -0.027 -0.032
## potam ~
## chla_1 (lb1) 0.069 0.061 1.132 0.258 0.069 0.054
## hzoop_1 (lb2) -0.083 0.051 -1.624 0.104 -0.083 -0.081
## pzoop_1 (lb3) -0.149 0.050 -2.983 0.003 -0.149 -0.147
## potam_1 (ls1) 0.633 0.049 13.014 0.000 0.633 0.633
## flow (la1) 0.049 0.062 0.785 0.432 0.049 0.041
## temp (la2) -0.048 0.055 -0.888 0.375 -0.048 -0.045
## turbid (la3) 0.059 0.059 1.012 0.312 0.059 0.054
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .din ~~
## .potam -0.044 0.044 -1.007 0.314 -0.044 -0.066
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .din 0.777 0.072 10.817 0.000 0.777 0.753
## .chla 0.605 0.056 10.817 0.000 0.605 0.913
## .potam 0.575 0.053 10.817 0.000 0.575 0.524
##
## R-Square:
## Estimate
## din 0.247
## chla 0.087
## potam 0.476
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ns 0.425 0.057 7.426 0.000 0.425 0.425
## nt 0.163 0.071 2.280 0.023 0.163 0.130
## nn 0.039 0.060 0.641 0.521 0.039 0.039
## na 0.207 0.071 2.925 0.003 0.207 0.196
## cb 0.011 0.051 0.219 0.827 0.011 0.014
## cs 0.258 0.063 4.091 0.000 0.258 0.262
## ct 0.020 0.056 0.364 0.716 0.020 0.026
## ca 0.125 0.053 2.357 0.018 0.125 0.150
## lb 0.184 0.050 3.679 0.000 0.184 0.176
## ls 0.633 0.049 13.014 0.000 0.633 0.633
## la 0.091 0.044 2.067 0.039 0.091 0.081summary(modfitW, standardized=T, rsq=T)## lavaan 0.6-9 ended normally after 25 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 27
##
## Used Total
## Number of observations 257 312
##
## Model Test User Model:
##
## Test statistic 6.563
## Degrees of freedom 3
## P-value (Chi-square) 0.087
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## din ~
## din_1 (ns1) 0.457 0.052 8.819 0.000 0.457 0.456
## chla (nt1) -0.138 0.053 -2.604 0.009 -0.138 -0.124
## hzoop_1 (nn1) -0.021 0.051 -0.413 0.679 -0.021 -0.022
## pzoop_1 (nn2) 0.059 0.049 1.201 0.230 0.059 0.059
## potam_1 (nn3) 0.099 0.054 1.851 0.064 0.099 0.100
## flow (na1) -0.308 0.054 -5.758 0.000 -0.308 -0.285
## temp (na2) 0.024 0.048 0.494 0.622 0.024 0.024
## turbid (na3) 0.092 0.051 1.800 0.072 0.092 0.092
## chla ~
## din_1 (cb1) -0.128 0.061 -2.117 0.034 -0.128 -0.142
## chla_1 (cs1) 0.148 0.065 2.297 0.022 0.148 0.149
## hzoop_1 (ct1) 0.095 0.058 1.651 0.099 0.095 0.109
## potam_1 (ct2) 0.033 0.062 0.536 0.592 0.033 0.037
## flow (ca1) 0.067 0.062 1.094 0.274 0.067 0.069
## temp (ca2) -0.057 0.055 -1.044 0.297 -0.057 -0.064
## turbid (ca3) -0.030 0.059 -0.514 0.607 -0.030 -0.034
## potam ~
## din_1 (lb1) 0.091 0.043 2.118 0.034 0.091 0.090
## chla_1 (lb2) -0.007 0.046 -0.151 0.880 -0.007 -0.006
## hzoop_1 (lb3) -0.044 0.043 -1.029 0.304 -0.044 -0.045
## pzoop_1 (lb4) 0.085 0.040 2.106 0.035 0.085 0.084
## potam_1 (ls1) 0.711 0.044 16.154 0.000 0.711 0.705
## flow (la1) -0.071 0.044 -1.625 0.104 -0.071 -0.065
## temp (la2) -0.011 0.039 -0.272 0.785 -0.011 -0.011
## turbid (la3) -0.087 0.042 -2.086 0.037 -0.087 -0.086
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .din ~~
## .potam 0.048 0.028 1.741 0.082 0.048 0.109
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .din 0.542 0.048 11.336 0.000 0.542 0.544
## .chla 0.724 0.064 11.336 0.000 0.724 0.898
## .potam 0.363 0.032 11.336 0.000 0.363 0.355
##
## R-Square:
## Estimate
## din 0.456
## chla 0.102
## potam 0.645
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ns 0.457 0.052 8.819 0.000 0.457 0.456
## nt 0.138 0.053 2.604 0.009 0.138 0.124
## nn 0.117 0.054 2.191 0.028 0.117 0.118
## na 0.322 0.055 5.814 0.000 0.322 0.300
## cb 0.128 0.061 2.117 0.034 0.128 0.142
## cs 0.148 0.065 2.297 0.022 0.148 0.149
## ct 0.101 0.063 1.615 0.106 0.101 0.115
## ca 0.093 0.061 1.534 0.125 0.093 0.100
## lb 0.132 0.042 3.136 0.002 0.132 0.131
## ls 0.711 0.044 16.154 0.000 0.711 0.705
## la 0.113 0.040 2.842 0.004 0.113 0.108summary(modfitN, standardized=T, rsq=T)## lavaan 0.6-9 ended normally after 15 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 27
##
## Used Total
## Number of observations 255 312
##
## Model Test User Model:
##
## Test statistic 6.773
## Degrees of freedom 3
## P-value (Chi-square) 0.080
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## din ~
## din_1 (ns1) 0.181 0.054 3.368 0.001 0.181 0.183
## chla (nt1) -0.165 0.051 -3.227 0.001 -0.165 -0.167
## hzoop_1 (nn1) 0.024 0.053 0.456 0.648 0.024 0.024
## pzoop_1 (nn2) 0.214 0.055 3.871 0.000 0.214 0.212
## corbic_1 (nn3) -0.053 0.053 -0.996 0.319 -0.053 -0.052
## flow (na1) -0.400 0.059 -6.764 0.000 -0.400 -0.370
## temp (na2) 0.052 0.053 0.984 0.325 0.052 0.052
## turbid (na3) 0.053 0.051 1.045 0.296 0.053 0.054
## chla ~
## din_1 (cb1) 0.034 0.064 0.528 0.598 0.034 0.034
## chla_1 (cs1) 0.280 0.060 4.647 0.000 0.280 0.282
## hzoop_1 (ct1) -0.059 0.062 -0.947 0.344 -0.059 -0.058
## corbic_1 (ct2) 0.015 0.062 0.237 0.813 0.015 0.014
## pzoop_1 (ct3) -0.162 0.065 -2.493 0.013 -0.162 -0.159
## flow (ca1) -0.030 0.069 -0.437 0.662 -0.030 -0.028
## temp (ca2) 0.140 0.061 2.293 0.022 0.140 0.140
## turbid (ca3) 0.075 0.059 1.273 0.203 0.075 0.077
## corbic ~
## chla_1 (lb1) 0.002 0.053 0.038 0.970 0.002 0.002
## hzoop_1 (lb2) 0.035 0.056 0.621 0.535 0.035 0.035
## pzoop_1 (lb3) -0.034 0.057 -0.584 0.559 -0.034 -0.033
## corbic_1 (ls1) 0.464 0.056 8.282 0.000 0.464 0.462
## flow (la1) 0.016 0.061 0.264 0.792 0.016 0.015
## temp (la2) -0.046 0.055 -0.836 0.403 -0.046 -0.047
## turbid (la3) -0.111 0.053 -2.086 0.037 -0.111 -0.115
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .din ~~
## .corbic -0.041 0.043 -0.959 0.337 -0.041 -0.060
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .din 0.644 0.057 11.292 0.000 0.644 0.654
## .chla 0.883 0.078 11.292 0.000 0.883 0.881
## .corbic 0.722 0.064 11.292 0.000 0.722 0.746
##
## R-Square:
## Estimate
## din 0.346
## chla 0.119
## corbic 0.254
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ns 0.181 0.054 3.368 0.001 0.181 0.183
## nt 0.165 0.051 3.227 0.001 0.165 0.167
## nn 0.222 0.053 4.199 0.000 0.222 0.220
## na 0.407 0.059 6.871 0.000 0.407 0.378
## cb 0.034 0.064 0.528 0.598 0.034 0.034
## cs 0.280 0.060 4.647 0.000 0.280 0.282
## ct 0.173 0.060 2.881 0.004 0.173 0.170
## ca 0.162 0.061 2.649 0.008 0.162 0.162
## lb 0.048 0.062 0.785 0.433 0.048 0.048
## ls 0.464 0.056 8.282 0.000 0.464 0.462
## la 0.121 0.054 2.229 0.026 0.121 0.125summary(modfitS, standardized=T, rsq=T)## lavaan 0.6-9 ended normally after 14 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 26
##
## Used Total
## Number of observations 256 312
##
## Model Test User Model:
##
## Test statistic 2.413
## Degrees of freedom 4
## P-value (Chi-square) 0.660
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## din ~
## din_1 (ns1) 0.195 0.061 3.178 0.001 0.195 0.195
## chla (nt1) 0.014 0.059 0.235 0.814 0.014 0.014
## hzoop_1 (nn1) -0.011 0.063 -0.170 0.865 -0.011 -0.010
## pzoop_1 (nn2) 0.021 0.064 0.333 0.739 0.021 0.020
## corbic_1 (nn3) 0.074 0.059 1.237 0.216 0.074 0.073
## flow (na1) -0.084 0.064 -1.321 0.187 -0.084 -0.079
## temp (na2) 0.089 0.060 1.496 0.135 0.089 0.088
## turbid (na3) 0.264 0.063 4.183 0.000 0.264 0.262
## chla ~
## din_1 (cb1) -0.015 0.062 -0.250 0.802 -0.015 -0.016
## chla_1 (cs1) 0.285 0.060 4.716 0.000 0.285 0.284
## hzoop_1 (ct1) 0.073 0.064 1.147 0.252 0.073 0.070
## corbic_1 (ct2) 0.078 0.060 1.299 0.194 0.078 0.078
## flow (ca1) -0.148 0.063 -2.336 0.019 -0.148 -0.141
## temp (ca2) 0.009 0.059 0.146 0.884 0.009 0.009
## turbid (ca3) 0.027 0.064 0.430 0.667 0.027 0.028
## corbic ~
## chla_1 (lb1) 0.052 0.059 0.874 0.382 0.052 0.051
## hzoop_1 (lb2) -0.026 0.061 -0.423 0.672 -0.026 -0.025
## pzoop_1 (lb3) -0.042 0.063 -0.662 0.508 -0.042 -0.039
## corbic_1 (ls1) 0.322 0.057 5.603 0.000 0.322 0.325
## flow (la1) 0.073 0.061 1.197 0.231 0.073 0.069
## temp (la2) -0.072 0.058 -1.245 0.213 -0.072 -0.072
## turbid (la3) 0.182 0.058 3.133 0.002 0.182 0.183
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .din ~~
## .corbic -0.070 0.053 -1.335 0.182 -0.070 -0.084
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .din 0.864 0.076 11.314 0.000 0.864 0.839
## .chla 0.874 0.077 11.314 0.000 0.874 0.875
## .corbic 0.813 0.072 11.314 0.000 0.813 0.810
##
## R-Square:
## Estimate
## din 0.161
## chla 0.125
## corbic 0.190
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ns 0.195 0.061 3.178 0.001 0.195 0.195
## nt 0.014 0.059 0.235 0.814 0.014 0.014
## nn 0.077 0.061 1.262 0.207 0.077 0.077
## na 0.291 0.066 4.433 0.000 0.291 0.287
## cb 0.015 0.062 0.250 0.802 0.015 0.016
## cs 0.285 0.060 4.716 0.000 0.285 0.284
## ct 0.107 0.058 1.824 0.068 0.107 0.105
## ca 0.151 0.065 2.328 0.020 0.151 0.143
## lb 0.071 0.066 1.081 0.280 0.071 0.069
## ls 0.322 0.057 5.603 0.000 0.322 0.325
## la 0.209 0.055 3.834 0.000 0.209 0.208#modificationindices(modfitW, sort=T, maximum.number=20)
#residuals(modfitW)
labelsfarwest=createLabels(modfitFW, cnameslag)
labelswest=createLabels(modfitW, cnameslag)
labelsnorth=createLabels(modfitN, cnameslag)
labelssouth=createLabels(modfitS, cnameslag)
#FAR WEST
myLavaanPlot(model=modfitFW, labels=labelsfarwest,
node_options=list(shape="box", fontname="Helvetica"),
coefs=TRUE, stand=TRUE, covs=FALSE, sig=0.05,
width=c("regress","latent"),
color=c("regress","latent"))lower_plot_far_west <- createGraph(fit=modfitFW,
reference_df=cnameslag,
model_type="monthly_lower_trophic",
title="Far West",
manual_port_settings=TRUE)
lower_plot_far_west#WEST
myLavaanPlot(model=modfitW, labels=labelswest,
node_options=list(shape="box", fontname="Helvetica"),
coefs=TRUE, stand=TRUE, covs=FALSE, sig=0.05,
width=c("regress","latent"),
color=c("regress","latent"))lower_plot_west <- createGraph(fit=modfitW,
reference_df=cnameslag,
model_type="monthly_lower_trophic",
title="West",
manual_port_settings=TRUE)
lower_plot_west#NORTH
myLavaanPlot(model=modfitN, labels=labelsnorth,
node_options=list(shape="box", fontname="Helvetica"),
coefs=TRUE, stand=TRUE, covs=FALSE, sig=0.05,
width=c("regress","latent"),
color=c("regress","latent"))lower_plot_north <- createGraph(fit=modfitN,
reference_df=cnameslag,
model_type="monthly_lower_trophic",
title="North",
manual_port_settings=TRUE)
lower_plot_north#SOUTH
myLavaanPlot(model=modfitS, labels=labelssouth,
node_options=list(shape="box", fontname="Helvetica"),
coefs=TRUE, stand=TRUE, covs=FALSE, sig=0.05,
width=c("regress","latent"),
color=c("regress","latent"))lower_plot_south <- createGraph(fit=modfitS,
reference_df=cnameslag,
model_type="monthly_lower_trophic",
title="South",
manual_port_settings=TRUE)
lower_plot_southSave updated SEM diagrams
Total effects
ssFW=standardizedsolution(modfitFW) %>% mutate(region="Far West")
ssW=standardizedsolution(modfitW) %>% mutate(region="West")
ssN=standardizedsolution(modfitN) %>% mutate(region="North")
ssS=standardizedsolution(modfitS) %>% mutate(region="South")
sslt=rbind(ssFW,ssW,ssN,ssS) %>% filter(op==":=") %>% select(region,lhs,est.std:ci.upper) %>%
separate(lhs,c("variable","influence"), sep=1) %>%
mutate(variable=case_when(variable=="n" ~ "DIN",
variable=="c" ~ "phytoplankton",
variable=="l" ~ "clams"),
influence=case_when(influence=="b" ~ "bottom-up",
influence=="t" ~ "top-down",
influence=="s" ~ "self-regulation",
influence=="a" ~ "abiotic drivers",
influence=="n" ~ "nutrient cycling"),
region=factor(region, levels=regionorder),
influence=factor(influence, levels=c("self-regulation","bottom-up","top-down","abiotic drivers","nutrient cycling")),
variable=factor(variable,levels=c("clams","phytoplankton","DIN")),
sig=ifelse(pvalue<0.05,"*",""))
ggplot(sslt,aes(x=influence,y=est.std)) +
facet_grid(variable~region) +
geom_errorbar(aes(ymin=ci.lower, ymax=ci.upper),width=0.5) +
geom_point() +
geom_text(aes(y=ci.upper+0.05, label=sig)) +
geom_hline(yintercept = 0) +
theme_bw() + theme(axis.text.x=element_text(angle=90, vjust=0.5, hjust=1)) +
labs(y="total effect (standardized)")
#ggsave("../lteffects.png",width = 6,height=5)Zooplankton-centered model (individual groups)
modFW='chla~chla_1+hcope_1+amphi_1+potam_1+flow+turbid+temp
hcope~chla_1+hcope_1+pcope_1+potam_1+flow+turbid+temp+estfish_bsmt_1
amphi~chla_1+amphi_1+flow+turbid+temp+estfish_bsmt_1
pcope~hcope_1+pcope_1+potam_1+flow+turbid+temp+estfish_bsmt_1
'
modW='chla~chla_1+hcope_1+amphi_1+potam_1+flow+turbid+temp+mysid_1
hcope~chla_1+hcope_1+pcope_1+mysid_1+potam_1+flow+turbid+temp+estfish_bsmt_1
amphi~chla_1+amphi_1+mysid_1+flow+turbid+temp+estfish_bsmt_1
pcope~hcope_1+pcope_1+mysid_1+potam_1+flow+turbid+temp+estfish_bsmt_1
mysid~chla_1+hcope_1+pcope_1+amphi_1+mysid_1+flow+turbid+temp+estfish_bsmt_1
'
modN='chla~chla_1+hcope_1+amphi_1+corbic_1+flow+turbid+temp
hcope~chla_1+hcope_1+pcope_1+mysid_1+corbic_1+flow+turbid+temp+estfish_bsmt_1
amphi~chla_1+amphi_1+flow+turbid+temp+estfish_bsmt_1
pcope~hcope_1+pcope_1+mysid_1+corbic_1+flow+turbid+temp+estfish_bsmt_1
mysid~hcope_1+pcope_1+mysid_1+amphi_1+flow+turbid+temp+estfish_bsmt_1
'
modS='chla~chla_1+hcope_1+clad_1+corbic_1+flow+turbid+temp
hcope~chla_1+hcope_1+pcope_1+corbic_1+flow+turbid+temp+estfish_bsmt_1
clad~chla_1+clad_1+pcope_1+flow+turbid+temp+estfish_bsmt_1
amphi~chla_1+amphi_1+flow+turbid+temp+estfish_bsmt_1
pcope~chla_1+hcope_1+clad_1+pcope_1+corbic_1+flow+turbid+temp+estfish_bsmt_1
'
modfitFW=sem(modFW, data=filter(fdr_ds,region=="Far West"))
modfitW=sem(modW, data=filter(fdr_ds,region=="West"))
modfitN=sem(modN, data=filter(fdr_ds,region=="North"))
modfitS=sem(modS, data=filter(fdr_ds,region=="South"))
summary(modfitFW, standardized=T, rsq=T)## lavaan 0.6-9 ended normally after 35 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 38
##
## Used Total
## Number of observations 203 312
##
## Model Test User Model:
##
## Test statistic 5.383
## Degrees of freedom 8
## P-value (Chi-square) 0.716
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## chla ~
## chla_1 0.230 0.067 3.411 0.001 0.230 0.231
## hcope_1 0.068 0.055 1.256 0.209 0.068 0.086
## amphi_1 0.020 0.059 0.336 0.737 0.020 0.025
## potam_1 -0.002 0.050 -0.044 0.965 -0.002 -0.003
## flow 0.012 0.070 0.174 0.861 0.012 0.014
## turbid -0.028 0.067 -0.412 0.680 -0.028 -0.032
## temp 0.107 0.059 1.803 0.071 0.107 0.127
## hcope ~
## chla_1 0.107 0.081 1.326 0.185 0.107 0.085
## hcope_1 0.239 0.068 3.487 0.000 0.239 0.239
## pcope_1 0.075 0.069 1.083 0.279 0.075 0.074
## potam_1 -0.146 0.062 -2.351 0.019 -0.146 -0.157
## flow -0.069 0.082 -0.843 0.399 -0.069 -0.062
## turbid -0.032 0.081 -0.391 0.696 -0.032 -0.029
## temp -0.060 0.073 -0.819 0.413 -0.060 -0.057
## estfish_bsmt_1 -0.130 0.073 -1.783 0.075 -0.130 -0.127
## amphi ~
## chla_1 0.030 0.039 0.774 0.439 0.030 0.024
## amphi_1 0.790 0.034 23.082 0.000 0.790 0.798
## flow -0.248 0.040 -6.202 0.000 -0.248 -0.221
## turbid 0.010 0.039 0.247 0.805 0.010 0.009
## temp 0.009 0.034 0.258 0.796 0.009 0.008
## estfish_bsmt_1 0.025 0.033 0.743 0.458 0.025 0.024
## pcope ~
## hcope_1 0.029 0.065 0.452 0.651 0.029 0.030
## pcope_1 0.278 0.066 4.231 0.000 0.278 0.281
## potam_1 -0.089 0.059 -1.497 0.134 -0.089 -0.098
## flow 0.253 0.078 3.233 0.001 0.253 0.231
## turbid 0.057 0.077 0.736 0.462 0.057 0.053
## temp 0.155 0.070 2.220 0.026 0.155 0.150
## estfish_bsmt_1 0.003 0.069 0.040 0.968 0.003 0.003
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .chla ~~
## .hcope 0.032 0.052 0.613 0.540 0.032 0.043
## .amphi 0.004 0.024 0.183 0.855 0.004 0.013
## .pcope 0.004 0.049 0.089 0.929 0.004 0.006
## .hcope ~~
## .amphi -0.004 0.030 -0.133 0.894 -0.004 -0.009
## .pcope -0.166 0.061 -2.723 0.006 -0.166 -0.195
## .amphi ~~
## .pcope 0.017 0.028 0.604 0.546 0.017 0.042
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .chla 0.606 0.060 10.075 0.000 0.606 0.910
## .hcope 0.897 0.089 10.075 0.000 0.897 0.850
## .amphi 0.199 0.020 10.075 0.000 0.199 0.190
## .pcope 0.815 0.081 10.075 0.000 0.815 0.809
##
## R-Square:
## Estimate
## chla 0.090
## hcope 0.150
## amphi 0.810
## pcope 0.191summary(modfitW, standardized=T, rsq=T)## lavaan 0.6-9 ended normally after 35 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 56
##
## Used Total
## Number of observations 215 312
##
## Model Test User Model:
##
## Test statistic 12.718
## Degrees of freedom 9
## P-value (Chi-square) 0.176
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## chla ~
## chla_1 0.174 0.066 2.622 0.009 0.174 0.177
## hcope_1 0.045 0.065 0.684 0.494 0.045 0.049
## amphi_1 0.165 0.061 2.689 0.007 0.165 0.191
## potam_1 -0.072 0.065 -1.110 0.267 -0.072 -0.081
## flow 0.131 0.068 1.929 0.054 0.131 0.130
## turbid 0.055 0.067 0.818 0.414 0.055 0.060
## temp -0.100 0.059 -1.698 0.090 -0.100 -0.112
## mysid_1 -0.131 0.065 -2.014 0.044 -0.131 -0.144
## hcope ~
## chla_1 0.095 0.067 1.418 0.156 0.095 0.089
## hcope_1 0.276 0.068 4.042 0.000 0.276 0.277
## pcope_1 -0.046 0.058 -0.800 0.424 -0.046 -0.050
## mysid_1 0.037 0.070 0.532 0.594 0.037 0.038
## potam_1 -0.194 0.064 -3.024 0.002 -0.194 -0.201
## flow -0.227 0.072 -3.155 0.002 -0.227 -0.207
## turbid -0.127 0.070 -1.811 0.070 -0.127 -0.127
## temp 0.046 0.062 0.737 0.461 0.046 0.047
## estfish_bsmt_1 0.028 0.059 0.475 0.634 0.028 0.030
## amphi ~
## chla_1 -0.063 0.039 -1.608 0.108 -0.063 -0.056
## amphi_1 0.794 0.037 21.276 0.000 0.794 0.800
## mysid_1 0.098 0.038 2.604 0.009 0.098 0.094
## flow 0.019 0.041 0.472 0.637 0.019 0.017
## turbid -0.122 0.040 -3.081 0.002 -0.122 -0.115
## temp -0.105 0.036 -2.935 0.003 -0.105 -0.102
## estfish_bsmt_1 -0.165 0.036 -4.582 0.000 -0.165 -0.164
## pcope ~
## hcope_1 -0.138 0.061 -2.240 0.025 -0.138 -0.132
## pcope_1 0.442 0.055 8.105 0.000 0.442 0.453
## mysid_1 0.129 0.064 2.002 0.045 0.129 0.124
## potam_1 0.012 0.060 0.196 0.844 0.012 0.012
## flow 0.193 0.066 2.942 0.003 0.193 0.169
## turbid -0.167 0.064 -2.584 0.010 -0.167 -0.159
## temp 0.213 0.056 3.802 0.000 0.213 0.210
## estfish_bsmt_1 0.002 0.056 0.038 0.970 0.002 0.002
## mysid ~
## chla_1 0.179 0.060 2.956 0.003 0.179 0.166
## hcope_1 0.052 0.059 0.883 0.377 0.052 0.052
## pcope_1 0.122 0.052 2.335 0.020 0.122 0.130
## amphi_1 -0.127 0.056 -2.267 0.023 -0.127 -0.134
## mysid_1 0.372 0.061 6.049 0.000 0.372 0.372
## flow -0.254 0.063 -4.049 0.000 -0.254 -0.230
## turbid 0.263 0.062 4.258 0.000 0.263 0.261
## temp 0.093 0.054 1.703 0.089 0.093 0.095
## estfish_bsmt_1 -0.025 0.054 -0.461 0.645 -0.025 -0.026
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .chla ~~
## .hcope 0.172 0.050 3.445 0.001 0.172 0.242
## .amphi -0.006 0.028 -0.225 0.822 -0.006 -0.015
## .pcope 0.015 0.045 0.336 0.737 0.015 0.023
## .mysid 0.085 0.043 1.966 0.049 0.085 0.135
## .hcope ~~
## .amphi -0.029 0.029 -1.000 0.317 -0.029 -0.068
## .pcope 0.117 0.047 2.472 0.013 0.117 0.171
## .mysid 0.170 0.046 3.695 0.000 0.170 0.260
## .amphi ~~
## .pcope 0.053 0.027 1.941 0.052 0.053 0.134
## .mysid -0.029 0.026 -1.101 0.271 -0.029 -0.075
## .pcope ~~
## .mysid 0.060 0.041 1.458 0.145 0.060 0.100
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .chla 0.684 0.066 10.368 0.000 0.684 0.853
## .hcope 0.743 0.072 10.368 0.000 0.743 0.788
## .amphi 0.251 0.024 10.368 0.000 0.251 0.236
## .pcope 0.629 0.061 10.368 0.000 0.629 0.609
## .mysid 0.575 0.055 10.368 0.000 0.575 0.601
##
## R-Square:
## Estimate
## chla 0.147
## hcope 0.212
## amphi 0.764
## pcope 0.391
## mysid 0.399summary(modfitN, standardized=T, rsq=T)## lavaan 0.6-9 ended normally after 33 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 53
##
## Used Total
## Number of observations 207 312
##
## Model Test User Model:
##
## Test statistic 17.901
## Degrees of freedom 12
## P-value (Chi-square) 0.119
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## chla ~
## chla_1 0.206 0.073 2.840 0.005 0.206 0.190
## hcope_1 -0.074 0.090 -0.821 0.411 -0.074 -0.060
## amphi_1 0.077 0.072 1.066 0.286 0.077 0.073
## corbic_1 0.002 0.071 0.025 0.980 0.002 0.002
## flow 0.081 0.079 1.032 0.302 0.081 0.074
## turbid 0.080 0.071 1.121 0.262 0.080 0.079
## temp 0.146 0.069 2.108 0.035 0.146 0.148
## hcope ~
## chla_1 -0.021 0.044 -0.481 0.631 -0.021 -0.025
## hcope_1 0.157 0.072 2.175 0.030 0.157 0.164
## pcope_1 -0.085 0.046 -1.861 0.063 -0.085 -0.116
## mysid_1 0.078 0.063 1.226 0.220 0.078 0.097
## corbic_1 0.087 0.043 2.019 0.044 0.087 0.107
## flow -0.317 0.054 -5.873 0.000 -0.317 -0.370
## turbid 0.068 0.050 1.362 0.173 0.068 0.086
## temp 0.127 0.045 2.799 0.005 0.127 0.166
## estfish_bsmt_1 0.026 0.047 0.555 0.579 0.026 0.035
## amphi ~
## chla_1 0.107 0.058 1.863 0.062 0.107 0.107
## amphi_1 0.533 0.057 9.356 0.000 0.533 0.542
## flow -0.006 0.064 -0.097 0.923 -0.006 -0.006
## turbid -0.014 0.056 -0.246 0.806 -0.014 -0.015
## temp -0.054 0.054 -0.997 0.319 -0.054 -0.059
## estfish_bsmt_1 -0.081 0.055 -1.491 0.136 -0.081 -0.093
## pcope ~
## hcope_1 -0.074 0.106 -0.700 0.484 -0.074 -0.058
## pcope_1 0.259 0.067 3.889 0.000 0.259 0.262
## mysid_1 0.137 0.092 1.489 0.137 0.137 0.128
## corbic_1 0.041 0.067 0.616 0.538 0.041 0.038
## flow -0.063 0.080 -0.794 0.427 -0.063 -0.055
## turbid -0.264 0.073 -3.592 0.000 -0.264 -0.252
## temp 0.079 0.067 1.178 0.239 0.079 0.077
## estfish_bsmt_1 -0.030 0.069 -0.440 0.660 -0.030 -0.031
## mysid ~
## hcope_1 0.018 0.088 0.203 0.839 0.018 0.015
## pcope_1 -0.051 0.056 -0.927 0.354 -0.051 -0.057
## mysid_1 0.208 0.076 2.738 0.006 0.208 0.210
## amphi_1 -0.100 0.052 -1.944 0.052 -0.100 -0.099
## flow -0.360 0.066 -5.463 0.000 -0.360 -0.340
## turbid 0.213 0.061 3.461 0.001 0.213 0.220
## temp 0.112 0.055 2.025 0.043 0.112 0.118
## estfish_bsmt_1 0.065 0.057 1.144 0.253 0.065 0.072
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .chla ~~
## .hcope 0.048 0.042 1.127 0.260 0.048 0.079
## .amphi 0.003 0.052 0.055 0.956 0.003 0.004
## .pcope -0.062 0.063 -0.994 0.320 -0.062 -0.069
## .mysid 0.107 0.053 2.040 0.041 0.107 0.143
## .hcope ~~
## .amphi 0.015 0.034 0.452 0.651 0.015 0.031
## .pcope 0.111 0.042 2.645 0.008 0.111 0.187
## .mysid 0.218 0.037 5.830 0.000 0.218 0.443
## .amphi ~~
## .pcope -0.119 0.051 -2.343 0.019 -0.119 -0.165
## .mysid 0.045 0.042 1.069 0.285 0.045 0.075
## .pcope ~~
## .mysid 0.193 0.052 3.687 0.000 0.193 0.265
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .chla 0.926 0.091 10.173 0.000 0.926 0.922
## .hcope 0.401 0.039 10.173 0.000 0.401 0.657
## .amphi 0.596 0.059 10.173 0.000 0.596 0.686
## .pcope 0.878 0.086 10.173 0.000 0.878 0.804
## .mysid 0.605 0.059 10.173 0.000 0.605 0.653
##
## R-Square:
## Estimate
## chla 0.078
## hcope 0.343
## amphi 0.314
## pcope 0.196
## mysid 0.347summary(modfitS, standardized=T, rsq=T)## lavaan 0.6-9 ended normally after 24 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 52
##
## Used Total
## Number of observations 210 312
##
## Model Test User Model:
##
## Test statistic 19.526
## Degrees of freedom 13
## P-value (Chi-square) 0.108
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## chla ~
## chla_1 0.220 0.070 3.149 0.002 0.220 0.213
## hcope_1 0.090 0.071 1.271 0.204 0.090 0.085
## clad_1 0.185 0.067 2.759 0.006 0.185 0.188
## corbic_1 -0.015 0.065 -0.237 0.813 -0.015 -0.015
## flow -0.138 0.080 -1.717 0.086 -0.138 -0.121
## turbid 0.013 0.066 0.193 0.847 0.013 0.013
## temp 0.060 0.065 0.913 0.361 0.060 0.059
## hcope ~
## chla_1 0.164 0.056 2.943 0.003 0.164 0.168
## hcope_1 0.291 0.061 4.757 0.000 0.291 0.290
## pcope_1 0.002 0.053 0.029 0.977 0.002 0.002
## corbic_1 0.110 0.055 1.980 0.048 0.110 0.113
## flow -0.296 0.066 -4.500 0.000 -0.296 -0.274
## turbid -0.076 0.056 -1.359 0.174 -0.076 -0.080
## temp 0.154 0.056 2.757 0.006 0.154 0.161
## estfish_bsmt_1 -0.182 0.056 -3.262 0.001 -0.182 -0.190
## clad ~
## chla_1 0.171 0.061 2.810 0.005 0.171 0.162
## clad_1 0.513 0.059 8.653 0.000 0.513 0.511
## pcope_1 -0.023 0.055 -0.416 0.677 -0.023 -0.023
## flow 0.125 0.066 1.889 0.059 0.125 0.107
## turbid -0.014 0.059 -0.242 0.809 -0.014 -0.014
## temp 0.135 0.059 2.303 0.021 0.135 0.130
## estfish_bsmt_1 -0.125 0.057 -2.206 0.027 -0.125 -0.121
## amphi ~
## chla_1 -0.026 0.070 -0.371 0.710 -0.026 -0.025
## amphi_1 0.208 0.067 3.094 0.002 0.208 0.205
## flow 0.066 0.079 0.830 0.407 0.066 0.055
## turbid 0.158 0.071 2.222 0.026 0.158 0.152
## temp 0.083 0.070 1.171 0.242 0.083 0.079
## estfish_bsmt_1 0.055 0.071 0.778 0.436 0.055 0.053
## pcope ~
## chla_1 0.243 0.065 3.729 0.000 0.243 0.232
## hcope_1 -0.058 0.069 -0.837 0.403 -0.058 -0.053
## clad_1 0.052 0.064 0.809 0.419 0.052 0.052
## pcope_1 0.446 0.062 7.189 0.000 0.446 0.448
## corbic_1 -0.043 0.062 -0.697 0.486 -0.043 -0.041
## flow 0.046 0.075 0.616 0.538 0.046 0.040
## turbid -0.089 0.063 -1.414 0.157 -0.089 -0.087
## temp 0.017 0.063 0.269 0.788 0.017 0.016
## estfish_bsmt_1 -0.056 0.063 -0.887 0.375 -0.056 -0.054
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .chla ~~
## .hcope 0.076 0.050 1.518 0.129 0.076 0.105
## .clad 0.206 0.055 3.773 0.000 0.206 0.270
## .amphi 0.028 0.064 0.437 0.662 0.028 0.030
## .pcope -0.017 0.056 -0.300 0.764 -0.017 -0.021
## .hcope ~~
## .clad 0.071 0.044 1.610 0.107 0.071 0.112
## .amphi 0.042 0.053 0.783 0.434 0.042 0.054
## .pcope 0.032 0.046 0.696 0.487 0.032 0.048
## .clad ~~
## .amphi -0.103 0.056 -1.831 0.067 -0.103 -0.127
## .pcope 0.094 0.050 1.897 0.058 0.094 0.132
## .amphi ~~
## .pcope 0.025 0.059 0.413 0.679 0.025 0.029
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .chla 0.872 0.085 10.247 0.000 0.872 0.857
## .hcope 0.600 0.059 10.247 0.000 0.600 0.660
## .clad 0.671 0.065 10.247 0.000 0.671 0.628
## .amphi 0.983 0.096 10.247 0.000 0.983 0.908
## .pcope 0.755 0.074 10.247 0.000 0.755 0.713
##
## R-Square:
## Estimate
## chla 0.143
## hcope 0.340
## clad 0.372
## amphi 0.092
## pcope 0.287#modificationindices(modfitS, sort=T, maximum.number=20)
#residuals(modfitW)
labelsfarwest=createLabels(modfitFW, cnameslag)
labelswest=createLabels(modfitW, cnameslag)
labelsnorth=createLabels(modfitN, cnameslag)
labelssouth=createLabels(modfitS, cnameslag)
#FAR WEST
myLavaanPlot(model=modfitFW, labels=labelsfarwest,
node_options=list(shape="box", fontname="Helvetica"),
coefs=TRUE, stand=TRUE, covs=FALSE, sig=0.05,
width=c("regress","latent"),
color=c("regress","latent"))zoop_plot_far_west <- createGraph(fit=modfitFW,
reference_df=cnameslag,
model_type="monthly_zoop",
region="Far West",
title="Far West",
manual_port_settings=TRUE)
zoop_plot_far_west#WEST
myLavaanPlot(model=modfitW, labels=labelswest,
node_options=list(shape="box", fontname="Helvetica"),
coefs=TRUE, stand=TRUE, covs=FALSE, sig=0.05,
width=c("regress","latent"),
color=c("regress","latent"))zoop_plot_west <- createGraph(fit=modfitW,
reference_df=cnameslag,
model_type="monthly_zoop",
region="West",
title="West",
manual_port_settings=TRUE)
zoop_plot_west#NORTH
myLavaanPlot(model=modfitN, labels=labelsnorth,
node_options=list(shape="box", fontname="Helvetica"),
coefs=TRUE, stand=TRUE, covs=FALSE, sig=0.05,
width=c("regress","latent"),
color=c("regress","latent"))zoop_plot_north <- createGraph(fit=modfitN,
reference_df=cnameslag,
model_type="monthly_zoop",
region="North",
title="North",
manual_port_settings=TRUE)
zoop_plot_north#SOUTH
myLavaanPlot(model=modfitS, labels=labelssouth,
node_options=list(shape="box", fontname="Helvetica"),
coefs=TRUE, stand=TRUE, covs=FALSE, sig=0.05,
width=c("regress","latent"),
color=c("regress","latent"))zoop_plot_south <- createGraph(fit=modfitS,
reference_df=cnameslag,
model_type="monthly_zoop",
region="South",
title="South",
manual_port_settings=TRUE)
zoop_plot_southSave updated SEM diagrams
zoop_grobs <- map(list(zoop_plot_far_west,
zoop_plot_west,
zoop_plot_north,
zoop_plot_south), ~convert_html_to_grob(.x, 2000))
zoop_figure <- ggarrange(plotlist=zoop_grobs, labels="auto",
font.label=list(size=11)) %>%
annotate_figure(top = text_grob("Monthly Regional Models (zooplankton groups)",
color = "black",
face = "bold",
size = 11))
ggsave('./fig_output/sem_zoop.png',zoop_figure, width=8, height=7, dpi=300)Total effects
Haven’t done yet.